Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md

Pull MD updates from Shaohua Li:

 - Add Partial Parity Log (ppl) feature found in Intel IMSM raid array
   by Artur Paszkiewicz. This feature is another way to close RAID5
   writehole. The Linux implementation is also available for normal
   RAID5 array if specific superblock bit is set.

 - A number of md-cluser fixes and enabling md-cluster array resize from
   Guoqing Jiang

 - A bunch of patches from Ming Lei and Neil Brown to rewrite MD bio
   handling related code. Now MD doesn't directly access bio bvec,
   bi_phys_segments and uses modern bio API for bio split.

 - Improve RAID5 IO pattern to improve performance for hard disk based
   RAID5/6 from me.

 - Several patches from Song Liu to speed up raid5-cache recovery and
   allow raid5 cache feature disabling in runtime.

 - Fix a performance regression in raid1 resync from Xiao Ni.

 - Other cleanup and fixes from various people.

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md: (84 commits)
  md/raid10: skip spare disk as 'first' disk
  md/raid1: Use a new variable to count flighting sync requests
  md: clear WantReplacement once disk is removed
  md/raid1/10: remove unused queue
  md: handle read-only member devices better.
  md/raid10: wait up frozen array in handle_write_completed
  uapi: fix linux/raid/md_p.h userspace compilation error
  md-cluster: Fix a memleak in an error handling path
  md: support disabling of create-on-open semantics.
  md: allow creation of mdNNN arrays via md_mod/parameters/new_array
  raid5-ppl: use a single mempool for ppl_io_unit and header_page
  md/raid0: fix up bio splitting.
  md/linear: improve bio splitting.
  md/raid5: make chunk_aligned_read() split bios more cleanly.
  md/raid10: simplify handle_read_error()
  md/raid10: simplify the splitting of requests.
  md/raid1: factor out flush_bio_list()
  md/raid1: simplify handle_read_error().
  Revert "block: introduce bio_copy_data_partial"
  md/raid1: simplify alloc_behind_master_bio()
  ...

1 files changed, 409 insertions, 234 deletions

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 2efdb0d67460..2e38cfac5b1d 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -58,11 +58,13 @@
 #include <linux/sched/signal.h>
 
 #include <trace/events/block.h>
+#include <linux/list_sort.h>
 
 #include "md.h"
 #include "raid5.h"
 #include "raid0.h"
 #include "bitmap.h"
+#include "raid5-log.h"
 
 #define UNSUPPORTED_MDDEV_FLAGS	(1L << MD_FAILFAST_SUPPORTED)
 
@@ -156,17 +158,6 @@ static int raid6_idx_to_slot(int idx, struct stripe_head *sh,
 	return slot;
 }
 
-static void return_io(struct bio_list *return_bi)
-{
-	struct bio *bi;
-	while ((bi = bio_list_pop(return_bi)) != NULL) {
-		bi->bi_iter.bi_size = 0;
-		trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
-					 bi, 0);
-		bio_endio(bi);
-	}
-}
-
 static void print_raid5_conf (struct r5conf *conf);
 
 static int stripe_operations_active(struct stripe_head *sh)
@@ -176,6 +167,13 @@ static int stripe_operations_active(struct stripe_head *sh)
 	       test_bit(STRIPE_COMPUTE_RUN, &sh->state);
 }
 
+static bool stripe_is_lowprio(struct stripe_head *sh)
+{
+	return (test_bit(STRIPE_R5C_FULL_STRIPE, &sh->state) ||
+		test_bit(STRIPE_R5C_PARTIAL_STRIPE, &sh->state)) &&
+	       !test_bit(STRIPE_R5C_CACHING, &sh->state);
+}
+
 static void raid5_wakeup_stripe_thread(struct stripe_head *sh)
 {
 	struct r5conf *conf = sh->raid_conf;
@@ -191,7 +189,10 @@ static void raid5_wakeup_stripe_thread(struct stripe_head *sh)
 	if (list_empty(&sh->lru)) {
 		struct r5worker_group *group;
 		group = conf->worker_groups + cpu_to_group(cpu);
-		list_add_tail(&sh->lru, &group->handle_list);
+		if (stripe_is_lowprio(sh))
+			list_add_tail(&sh->lru, &group->loprio_list);
+		else
+			list_add_tail(&sh->lru, &group->handle_list);
 		group->stripes_cnt++;
 		sh->group = group;
 	}
@@ -254,7 +255,12 @@ static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh,
 			clear_bit(STRIPE_DELAYED, &sh->state);
 			clear_bit(STRIPE_BIT_DELAY, &sh->state);
 			if (conf->worker_cnt_per_group == 0) {
-				list_add_tail(&sh->lru, &conf->handle_list);
+				if (stripe_is_lowprio(sh))
+					list_add_tail(&sh->lru,
+							&conf->loprio_list);
+				else
+					list_add_tail(&sh->lru,
+							&conf->handle_list);
 			} else {
 				raid5_wakeup_stripe_thread(sh);
 				return;
@@ -481,6 +487,7 @@ static int grow_buffers(struct stripe_head *sh, gfp_t gfp)
 		sh->dev[i].page = page;
 		sh->dev[i].orig_page = page;
 	}
+
 	return 0;
 }
 
@@ -729,7 +736,7 @@ static bool stripe_can_batch(struct stripe_head *sh)
 {
 	struct r5conf *conf = sh->raid_conf;
 
-	if (conf->log)
+	if (conf->log || raid5_has_ppl(conf))
 		return false;
 	return test_bit(STRIPE_BATCH_READY, &sh->state) &&
 		!test_bit(STRIPE_BITMAP_PENDING, &sh->state) &&
@@ -863,41 +870,107 @@ static int use_new_offset(struct r5conf *conf, struct stripe_head *sh)
 	return 1;
 }
 
-static void flush_deferred_bios(struct r5conf *conf)
+static void dispatch_bio_list(struct bio_list *tmp)
 {
-	struct bio_list tmp;
 	struct bio *bio;
 
-	if (!conf->batch_bio_dispatch || !conf->group_cnt)
+	while ((bio = bio_list_pop(tmp)))
+		generic_make_request(bio);
+}
+
+static int cmp_stripe(void *priv, struct list_head *a, struct list_head *b)
+{
+	const struct r5pending_data *da = list_entry(a,
+				struct r5pending_data, sibling);
+	const struct r5pending_data *db = list_entry(b,
+				struct r5pending_data, sibling);
+	if (da->sector > db->sector)
+		return 1;
+	if (da->sector < db->sector)
+		return -1;
+	return 0;
+}
+
+static void dispatch_defer_bios(struct r5conf *conf, int target,
+				struct bio_list *list)
+{
+	struct r5pending_data *data;
+	struct list_head *first, *next = NULL;
+	int cnt = 0;
+
+	if (conf->pending_data_cnt == 0)
+		return;
+
+	list_sort(NULL, &conf->pending_list, cmp_stripe);
+
+	first = conf->pending_list.next;
+
+	/* temporarily move the head */
+	if (conf->next_pending_data)
+		list_move_tail(&conf->pending_list,
+				&conf->next_pending_data->sibling);
+
+	while (!list_empty(&conf->pending_list)) {
+		data = list_first_entry(&conf->pending_list,
+			struct r5pending_data, sibling);
+		if (&data->sibling == first)
+			first = data->sibling.next;
+		next = data->sibling.next;
+
+		bio_list_merge(list, &data->bios);
+		list_move(&data->sibling, &conf->free_list);
+		cnt++;
+		if (cnt >= target)
+			break;
+	}
+	conf->pending_data_cnt -= cnt;
+	BUG_ON(conf->pending_data_cnt < 0 || cnt < target);
+
+	if (next != &conf->pending_list)
+		conf->next_pending_data = list_entry(next,
+				struct r5pending_data, sibling);
+	else
+		conf->next_pending_data = NULL;
+	/* list isn't empty */
+	if (first != &conf->pending_list)
+		list_move_tail(&conf->pending_list, first);
+}
+
+static void flush_deferred_bios(struct r5conf *conf)
+{
+	struct bio_list tmp = BIO_EMPTY_LIST;
+
+	if (conf->pending_data_cnt == 0)
 		return;
 
-	bio_list_init(&tmp);
 	spin_lock(&conf->pending_bios_lock);
-	bio_list_merge(&tmp, &conf->pending_bios);
-	bio_list_init(&conf->pending_bios);
+	dispatch_defer_bios(conf, conf->pending_data_cnt, &tmp);
+	BUG_ON(conf->pending_data_cnt != 0);
 	spin_unlock(&conf->pending_bios_lock);
 
-	while ((bio = bio_list_pop(&tmp)))
-		generic_make_request(bio);
+	dispatch_bio_list(&tmp);
 }
 
-static void defer_bio_issue(struct r5conf *conf, struct bio *bio)
+static void defer_issue_bios(struct r5conf *conf, sector_t sector,
+				struct bio_list *bios)
 {
-	/*
-	 * change group_cnt will drain all bios, so this is safe
-	 *
-	 * A read generally means a read-modify-write, which usually means a
-	 * randwrite, so we don't delay it
-	 */
-	if (!conf->batch_bio_dispatch || !conf->group_cnt ||
-	    bio_op(bio) == REQ_OP_READ) {
-		generic_make_request(bio);
-		return;
-	}
+	struct bio_list tmp = BIO_EMPTY_LIST;
+	struct r5pending_data *ent;
+
 	spin_lock(&conf->pending_bios_lock);
-	bio_list_add(&conf->pending_bios, bio);
+	ent = list_first_entry(&conf->free_list, struct r5pending_data,
+							sibling);
+	list_move_tail(&ent->sibling, &conf->pending_list);
+	ent->sector = sector;
+	bio_list_init(&ent->bios);
+	bio_list_merge(&ent->bios, bios);
+	conf->pending_data_cnt++;
+	if (conf->pending_data_cnt >= PENDING_IO_MAX)
+		dispatch_defer_bios(conf, PENDING_IO_ONE_FLUSH, &tmp);
+
 	spin_unlock(&conf->pending_bios_lock);
-	md_wakeup_thread(conf->mddev->thread);
+
+	dispatch_bio_list(&tmp);
 }
 
 static void
@@ -910,21 +983,15 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 	struct r5conf *conf = sh->raid_conf;
 	int i, disks = sh->disks;
 	struct stripe_head *head_sh = sh;
+	struct bio_list pending_bios = BIO_EMPTY_LIST;
+	bool should_defer;
 
 	might_sleep();
 
-	if (!test_bit(STRIPE_R5C_CACHING, &sh->state)) {
-		/* writing out phase */
-		if (s->waiting_extra_page)
-			return;
-		if (r5l_write_stripe(conf->log, sh) == 0)
-			return;
-	} else {  /* caching phase */
-		if (test_bit(STRIPE_LOG_TRAPPED, &sh->state)) {
-			r5c_cache_data(conf->log, sh, s);
-			return;
-		}
-	}
+	if (log_stripe(sh, s) == 0)
+		return;
+
+	should_defer = conf->batch_bio_dispatch && conf->group_cnt;
 
 	for (i = disks; i--; ) {
 		int op, op_flags = 0;
@@ -1080,7 +1147,10 @@ again:
 				trace_block_bio_remap(bdev_get_queue(bi->bi_bdev),
 						      bi, disk_devt(conf->mddev->gendisk),
 						      sh->dev[i].sector);
-			defer_bio_issue(conf, bi);
+			if (should_defer && op_is_write(op))
+				bio_list_add(&pending_bios, bi);
+			else
+				generic_make_request(bi);
 		}
 		if (rrdev) {
 			if (s->syncing || s->expanding || s->expanded
@@ -1125,7 +1195,10 @@ again:
 				trace_block_bio_remap(bdev_get_queue(rbi->bi_bdev),
 						      rbi, disk_devt(conf->mddev->gendisk),
 						      sh->dev[i].sector);
-			defer_bio_issue(conf, rbi);
+			if (should_defer && op_is_write(op))
+				bio_list_add(&pending_bios, rbi);
+			else
+				generic_make_request(rbi);
 		}
 		if (!rdev && !rrdev) {
 			if (op_is_write(op))
@@ -1143,6 +1216,9 @@ again:
 		if (sh != head_sh)
 			goto again;
 	}
+
+	if (should_defer && !bio_list_empty(&pending_bios))
+		defer_issue_bios(conf, head_sh->sector, &pending_bios);
 }
 
 static struct dma_async_tx_descriptor *
@@ -1212,7 +1288,6 @@ async_copy_data(int frombio, struct bio *bio, struct page **page,
 static void ops_complete_biofill(void *stripe_head_ref)
 {
 	struct stripe_head *sh = stripe_head_ref;
-	struct bio_list return_bi = BIO_EMPTY_LIST;
 	int i;
 
 	pr_debug("%s: stripe %llu\n", __func__,
@@ -1236,16 +1311,13 @@ static void ops_complete_biofill(void *stripe_head_ref)
 			while (rbi && rbi->bi_iter.bi_sector <
 				dev->sector + STRIPE_SECTORS) {
 				rbi2 = r5_next_bio(rbi, dev->sector);
-				if (!raid5_dec_bi_active_stripes(rbi))
-					bio_list_add(&return_bi, rbi);
+				bio_endio(rbi);
 				rbi = rbi2;
 			}
 		}
 	}
 	clear_bit(STRIPE_BIOFILL_RUN, &sh->state);
 
-	return_io(&return_bi);
-
 	set_bit(STRIPE_HANDLE, &sh->state);
 	raid5_release_stripe(sh);
 }
@@ -2014,6 +2086,9 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
 			tx = ops_run_prexor6(sh, percpu, tx);
 	}
 
+	if (test_bit(STRIPE_OP_PARTIAL_PARITY, &ops_request))
+		tx = ops_run_partial_parity(sh, percpu, tx);
+
 	if (test_bit(STRIPE_OP_BIODRAIN, &ops_request)) {
 		tx = ops_run_biodrain(sh, tx);
 		overlap_clear++;
@@ -2046,8 +2121,15 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
 	put_cpu();
 }
 
+static void free_stripe(struct kmem_cache *sc, struct stripe_head *sh)
+{
+	if (sh->ppl_page)
+		__free_page(sh->ppl_page);
+	kmem_cache_free(sc, sh);
+}
+
 static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp,
-	int disks)
+	int disks, struct r5conf *conf)
 {
 	struct stripe_head *sh;
 	int i;
@@ -2061,6 +2143,7 @@ static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp,
 		INIT_LIST_HEAD(&sh->r5c);
 		INIT_LIST_HEAD(&sh->log_list);
 		atomic_set(&sh->count, 1);
+		sh->raid_conf = conf;
 		sh->log_start = MaxSector;
 		for (i = 0; i < disks; i++) {
 			struct r5dev *dev = &sh->dev[i];
@@ -2068,6 +2151,14 @@ static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp,
 			bio_init(&dev->req, &dev->vec, 1);
 			bio_init(&dev->rreq, &dev->rvec, 1);
 		}
+
+		if (raid5_has_ppl(conf)) {
+			sh->ppl_page = alloc_page(gfp);
+			if (!sh->ppl_page) {
+				free_stripe(sc, sh);
+				sh = NULL;
+			}
+		}
 	}
 	return sh;
 }
@@ -2075,15 +2166,13 @@ static int grow_one_stripe(struct r5conf *conf, gfp_t gfp)
 {
 	struct stripe_head *sh;
 
-	sh = alloc_stripe(conf->slab_cache, gfp, conf->pool_size);
+	sh = alloc_stripe(conf->slab_cache, gfp, conf->pool_size, conf);
 	if (!sh)
 		return 0;
 
-	sh->raid_conf = conf;
-
 	if (grow_buffers(sh, gfp)) {
 		shrink_buffers(sh);
-		kmem_cache_free(conf->slab_cache, sh);
+		free_stripe(conf->slab_cache, sh);
 		return 0;
 	}
 	sh->hash_lock_index =
@@ -2210,7 +2299,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 	 *    pages have been transferred over, and the old kmem_cache is
 	 *    freed when all stripes are done.
 	 * 3/ reallocate conf->disks to be suitable bigger.  If this fails,
-	 *    we simple return a failre status - no need to clean anything up.
+	 *    we simple return a failure status - no need to clean anything up.
 	 * 4/ allocate new pages for the new slots in the new stripe_heads.
 	 *    If this fails, we don't bother trying the shrink the
 	 *    stripe_heads down again, we just leave them as they are.
@@ -2228,9 +2317,6 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 	int i;
 	int hash, cnt;
 
-	if (newsize <= conf->pool_size)
-		return 0; /* never bother to shrink */
-
 	err = md_allow_write(conf->mddev);
 	if (err)
 		return err;
@@ -2246,11 +2332,10 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 	mutex_lock(&conf->cache_size_mutex);
 
 	for (i = conf->max_nr_stripes; i; i--) {
-		nsh = alloc_stripe(sc, GFP_KERNEL, newsize);
+		nsh = alloc_stripe(sc, GFP_KERNEL, newsize, conf);
 		if (!nsh)
 			break;
 
-		nsh->raid_conf = conf;
 		list_add(&nsh->lru, &newstripes);
 	}
 	if (i) {
@@ -2258,7 +2343,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 		while (!list_empty(&newstripes)) {
 			nsh = list_entry(newstripes.next, struct stripe_head, lru);
 			list_del(&nsh->lru);
-			kmem_cache_free(sc, nsh);
+			free_stripe(sc, nsh);
 		}
 		kmem_cache_destroy(sc);
 		mutex_unlock(&conf->cache_size_mutex);
@@ -2284,7 +2369,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 			nsh->dev[i].orig_page = osh->dev[i].page;
 		}
 		nsh->hash_lock_index = hash;
-		kmem_cache_free(conf->slab_cache, osh);
+		free_stripe(conf->slab_cache, osh);
 		cnt++;
 		if (cnt >= conf->max_nr_stripes / NR_STRIPE_HASH_LOCKS +
 		    !!((conf->max_nr_stripes % NR_STRIPE_HASH_LOCKS) > hash)) {
@@ -2323,6 +2408,10 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 		err = -ENOMEM;
 
 	mutex_unlock(&conf->cache_size_mutex);
+
+	conf->slab_cache = sc;
+	conf->active_name = 1-conf->active_name;
+
 	/* Step 4, return new stripes to service */
 	while(!list_empty(&newstripes)) {
 		nsh = list_entry(newstripes.next, struct stripe_head, lru);
@@ -2340,8 +2429,6 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 	}
 	/* critical section pass, GFP_NOIO no longer needed */
 
-	conf->slab_cache = sc;
-	conf->active_name = 1-conf->active_name;
 	if (!err)
 		conf->pool_size = newsize;
 	return err;
@@ -2359,7 +2446,7 @@ static int drop_one_stripe(struct r5conf *conf)
 		return 0;
 	BUG_ON(atomic_read(&sh->count));
 	shrink_buffers(sh);
-	kmem_cache_free(conf->slab_cache, sh);
+	free_stripe(conf->slab_cache, sh);
 	atomic_dec(&conf->active_stripes);
 	conf->max_nr_stripes--;
 	return 1;
@@ -3082,6 +3169,12 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s,
 		s->locked++;
 	}
 
+	if (raid5_has_ppl(sh->raid_conf) && sh->ppl_page &&
+	    test_bit(STRIPE_OP_BIODRAIN, &s->ops_request) &&
+	    !test_bit(STRIPE_FULL_WRITE, &sh->state) &&
+	    test_bit(R5_Insync, &sh->dev[pd_idx].flags))
+		set_bit(STRIPE_OP_PARTIAL_PARITY, &s->ops_request);
+
 	pr_debug("%s: stripe %llu locked: %d ops_request: %lx\n",
 		__func__, (unsigned long long)sh->sector,
 		s->locked, s->ops_request);
@@ -3103,14 +3196,6 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx,
 		(unsigned long long)bi->bi_iter.bi_sector,
 		(unsigned long long)sh->sector);
 
-	/*
-	 * If several bio share a stripe. The bio bi_phys_segments acts as a
-	 * reference count to avoid race. The reference count should already be
-	 * increased before this function is called (for example, in
-	 * raid5_make_request()), so other bio sharing this stripe will not free the
-	 * stripe. If a stripe is owned by one stripe, the stripe lock will
-	 * protect it.
-	 */
 	spin_lock_irq(&sh->stripe_lock);
 	/* Don't allow new IO added to stripes in batch list */
 	if (sh->batch_head)
@@ -3129,6 +3214,36 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx,
 	if (*bip && (*bip)->bi_iter.bi_sector < bio_end_sector(bi))
 		goto overlap;
 
+	if (forwrite && raid5_has_ppl(conf)) {
+		/*
+		 * With PPL only writes to consecutive data chunks within a
+		 * stripe are allowed because for a single stripe_head we can
+		 * only have one PPL entry at a time, which describes one data
+		 * range. Not really an overlap, but wait_for_overlap can be
+		 * used to handle this.
+		 */
+		sector_t sector;
+		sector_t first = 0;
+		sector_t last = 0;
+		int count = 0;
+		int i;
+
+		for (i = 0; i < sh->disks; i++) {
+			if (i != sh->pd_idx &&
+			    (i == dd_idx || sh->dev[i].towrite)) {
+				sector = sh->dev[i].sector;
+				if (count == 0 || sector < first)
+					first = sector;
+				if (sector > last)
+					last = sector;
+				count++;
+			}
+		}
+
+		if (first + conf->chunk_sectors * (count - 1) != last)
+			goto overlap;
+	}
+
 	if (!forwrite || previous)
 		clear_bit(STRIPE_BATCH_READY, &sh->state);
 
@@ -3136,7 +3251,8 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx,
 	if (*bip)
 		bi->bi_next = *bip;
 	*bip = bi;
-	raid5_inc_bi_active_stripes(bi);
+	bio_inc_remaining(bi);
+	md_write_inc(conf->mddev, bi);
 
 	if (forwrite) {
 		/* check if page is covered */
@@ -3213,8 +3329,7 @@ static void stripe_set_idx(sector_t stripe, struct r5conf *conf, int previous,
 
 static void
 handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
-				struct stripe_head_state *s, int disks,
-				struct bio_list *return_bi)
+		     struct stripe_head_state *s, int disks)
 {
 	int i;
 	BUG_ON(sh->batch_head);
@@ -3250,7 +3365,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 		if (bi)
 			bitmap_end = 1;
 
-		r5l_stripe_write_finished(sh);
+		log_stripe_write_finished(sh);
 
 		if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
 			wake_up(&conf->wait_for_overlap);
@@ -3260,10 +3375,8 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 			struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector);
 
 			bi->bi_error = -EIO;
-			if (!raid5_dec_bi_active_stripes(bi)) {
-				md_write_end(conf->mddev);
-				bio_list_add(return_bi, bi);
-			}
+			md_write_end(conf->mddev);
+			bio_endio(bi);
 			bi = nextbi;
 		}
 		if (bitmap_end)
@@ -3284,10 +3397,8 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 			struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);
 
 			bi->bi_error = -EIO;
-			if (!raid5_dec_bi_active_stripes(bi)) {
-				md_write_end(conf->mddev);
-				bio_list_add(return_bi, bi);
-			}
+			md_write_end(conf->mddev);
+			bio_endio(bi);
 			bi = bi2;
 		}
 
@@ -3312,8 +3423,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 					r5_next_bio(bi, sh->dev[i].sector);
 
 				bi->bi_error = -EIO;
-				if (!raid5_dec_bi_active_stripes(bi))
-					bio_list_add(return_bi, bi);
+				bio_endio(bi);
 				bi = nextbi;
 			}
 		}
@@ -3449,7 +3559,7 @@ static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s,
 	    !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
 		/* Pre-reads at not permitted until after short delay
 		 * to gather multiple requests.  However if this
-		 * device is no Insync, the block could only be be computed
+		 * device is no Insync, the block could only be computed
 		 * and there is no need to delay that.
 		 */
 		return 0;
@@ -3468,7 +3578,7 @@ static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s,
 
 	/* If we are forced to do a reconstruct-write, either because
 	 * the current RAID6 implementation only supports that, or
-	 * or because parity cannot be trusted and we are currently
+	 * because parity cannot be trusted and we are currently
 	 * recovering it, there is extra need to be careful.
 	 * If one of the devices that we would need to read, because
 	 * it is not being overwritten (and maybe not written at all)
@@ -3508,9 +3618,20 @@ static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s,
 		BUG_ON(test_bit(R5_Wantcompute, &dev->flags));
 		BUG_ON(test_bit(R5_Wantread, &dev->flags));
 		BUG_ON(sh->batch_head);
+
+		/*
+		 * In the raid6 case if the only non-uptodate disk is P
+		 * then we already trusted P to compute the other failed
+		 * drives. It is safe to compute rather than re-read P.
+		 * In other cases we only compute blocks from failed
+		 * devices, otherwise check/repair might fail to detect
+		 * a real inconsistency.
+		 */
+
 		if ((s->uptodate == disks - 1) &&
+		    ((sh->qd_idx >= 0 && sh->pd_idx == disk_idx) ||
 		    (s->failed && (disk_idx == s->failed_num[0] ||
-				   disk_idx == s->failed_num[1]))) {
+				   disk_idx == s->failed_num[1])))) {
 			/* have disk failed, and we're requested to fetch it;
 			 * do compute it
 			 */
@@ -3612,7 +3733,7 @@ static void break_stripe_batch_list(struct stripe_head *head_sh,
  * never LOCKED, so we don't need to test 'failed' directly.
  */
 static void handle_stripe_clean_event(struct r5conf *conf,
-	struct stripe_head *sh, int disks, struct bio_list *return_bi)
+	struct stripe_head *sh, int disks)
 {
 	int i;
 	struct r5dev *dev;
@@ -3644,10 +3765,8 @@ returnbi:
 				while (wbi && wbi->bi_iter.bi_sector <
 					dev->sector + STRIPE_SECTORS) {
 					wbi2 = r5_next_bio(wbi, dev->sector);
-					if (!raid5_dec_bi_active_stripes(wbi)) {
-						md_write_end(conf->mddev);
-						bio_list_add(return_bi, wbi);
-					}
+					md_write_end(conf->mddev);
+					bio_endio(wbi);
 					wbi = wbi2;
 				}
 				bitmap_endwrite(conf->mddev->bitmap, sh->sector,
@@ -3669,7 +3788,7 @@ returnbi:
 				discard_pending = 1;
 		}
 
-	r5l_stripe_write_finished(sh);
+	log_stripe_write_finished(sh);
 
 	if (!discard_pending &&
 	    test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags)) {
@@ -4556,7 +4675,8 @@ static void handle_stripe(struct stripe_head *sh)
 	if (test_bit(STRIPE_LOG_TRAPPED, &sh->state))
 		goto finish;
 
-	if (s.handle_bad_blocks) {
+	if (s.handle_bad_blocks ||
+	    test_bit(MD_SB_CHANGE_PENDING, &conf->mddev->sb_flags)) {
 		set_bit(STRIPE_HANDLE, &sh->state);
 		goto finish;
 	}
@@ -4589,7 +4709,7 @@ static void handle_stripe(struct stripe_head *sh)
 		sh->reconstruct_state = 0;
 		break_stripe_batch_list(sh, 0);
 		if (s.to_read+s.to_write+s.written)
-			handle_failed_stripe(conf, sh, &s, disks, &s.return_bi);
+			handle_failed_stripe(conf, sh, &s, disks);
 		if (s.syncing + s.replacing)
 			handle_failed_sync(conf, sh, &s);
 	}
@@ -4655,11 +4775,11 @@ static void handle_stripe(struct stripe_head *sh)
 			     && !test_bit(R5_LOCKED, &qdev->flags)
 			     && (test_bit(R5_UPTODATE, &qdev->flags) ||
 				 test_bit(R5_Discard, &qdev->flags))))))
-		handle_stripe_clean_event(conf, sh, disks, &s.return_bi);
+		handle_stripe_clean_event(conf, sh, disks);
 
 	if (s.just_cached)
-		r5c_handle_cached_data_endio(conf, sh, disks, &s.return_bi);
-	r5l_stripe_write_finished(sh);
+		r5c_handle_cached_data_endio(conf, sh, disks);
+	log_stripe_write_finished(sh);
 
 	/* Now we might consider reading some blocks, either to check/generate
 	 * parity, or to satisfy requests
@@ -4886,16 +5006,6 @@ finish:
 			md_wakeup_thread(conf->mddev->thread);
 	}
 
-	if (!bio_list_empty(&s.return_bi)) {
-		if (test_bit(MD_SB_CHANGE_PENDING, &conf->mddev->sb_flags)) {
-			spin_lock_irq(&conf->device_lock);
-			bio_list_merge(&conf->return_bi, &s.return_bi);
-			spin_unlock_irq(&conf->device_lock);
-			md_wakeup_thread(conf->mddev->thread);
-		} else
-			return_io(&s.return_bi);
-	}
-
 	clear_bit_unlock(STRIPE_ACTIVE, &sh->state);
 }
 
@@ -4984,12 +5094,14 @@ static void add_bio_to_retry(struct bio *bi,struct r5conf *conf)
 	md_wakeup_thread(conf->mddev->thread);
 }
 
-static struct bio *remove_bio_from_retry(struct r5conf *conf)
+static struct bio *remove_bio_from_retry(struct r5conf *conf,
+					 unsigned int *offset)
 {
 	struct bio *bi;
 
 	bi = conf->retry_read_aligned;
 	if (bi) {
+		*offset = conf->retry_read_offset;
 		conf->retry_read_aligned = NULL;
 		return bi;
 	}
@@ -4997,11 +5109,7 @@ static struct bio *remove_bio_from_retry(struct r5conf *conf)
 	if(bi) {
 		conf->retry_read_aligned_list = bi->bi_next;
 		bi->bi_next = NULL;
-		/*
-		 * this sets the active strip count to 1 and the processed
-		 * strip count to zero (upper 8 bits)
-		 */
-		raid5_set_bi_stripes(bi, 1); /* biased count of active stripes */
+		*offset = 0;
 	}
 
 	return bi;
@@ -5136,24 +5244,20 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio)
 {
 	struct bio *split;
+	sector_t sector = raid_bio->bi_iter.bi_sector;
+	unsigned chunk_sects = mddev->chunk_sectors;
+	unsigned sectors = chunk_sects - (sector & (chunk_sects-1));
 
-	do {
-		sector_t sector = raid_bio->bi_iter.bi_sector;
-		unsigned chunk_sects = mddev->chunk_sectors;
-		unsigned sectors = chunk_sects - (sector & (chunk_sects-1));
-
-		if (sectors < bio_sectors(raid_bio)) {
-			split = bio_split(raid_bio, sectors, GFP_NOIO, fs_bio_set);
-			bio_chain(split, raid_bio);
-		} else
-			split = raid_bio;
+	if (sectors < bio_sectors(raid_bio)) {
+		struct r5conf *conf = mddev->private;
+		split = bio_split(raid_bio, sectors, GFP_NOIO, conf->bio_split);
+		bio_chain(split, raid_bio);
+		generic_make_request(raid_bio);
+		raid_bio = split;
+	}
 
-		if (!raid5_read_one_chunk(mddev, split)) {
-			if (split != raid_bio)
-				generic_make_request(raid_bio);
-			return split;
-		}
-	} while (split != raid_bio);
+	if (!raid5_read_one_chunk(mddev, raid_bio))
+		return raid_bio;
 
 	return NULL;
 }
@@ -5170,19 +5274,27 @@ static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio)
  */
 static struct stripe_head *__get_priority_stripe(struct r5conf *conf, int group)
 {
-	struct stripe_head *sh = NULL, *tmp;
+	struct stripe_head *sh, *tmp;
 	struct list_head *handle_list = NULL;
-	struct r5worker_group *wg = NULL;
+	struct r5worker_group *wg;
+	bool second_try = !r5c_is_writeback(conf->log);
+	bool try_loprio = test_bit(R5C_LOG_TIGHT, &conf->cache_state);
 
+again:
+	wg = NULL;
+	sh = NULL;
 	if (conf->worker_cnt_per_group == 0) {
-		handle_list = &conf->handle_list;
+		handle_list = try_loprio ? &conf->loprio_list :
+					&conf->handle_list;
 	} else if (group != ANY_GROUP) {
-		handle_list = &conf->worker_groups[group].handle_list;
+		handle_list = try_loprio ? &conf->worker_groups[group].loprio_list :
+				&conf->worker_groups[group].handle_list;
 		wg = &conf->worker_groups[group];
 	} else {
 		int i;
 		for (i = 0; i < conf->group_cnt; i++) {
-			handle_list = &conf->worker_groups[i].handle_list;
+			handle_list = try_loprio ? &conf->worker_groups[i].loprio_list :
+				&conf->worker_groups[i].handle_list;
 			wg = &conf->worker_groups[i];
 			if (!list_empty(handle_list))
 				break;
@@ -5233,8 +5345,13 @@ static struct stripe_head *__get_priority_stripe(struct r5conf *conf, int group)
 		wg = NULL;
 	}
 
-	if (!sh)
-		return NULL;
+	if (!sh) {
+		if (second_try)
+			return NULL;
+		second_try = true;
+		try_loprio = !try_loprio;
+		goto again;
+	}
 
 	if (wg) {
 		wg->stripes_cnt--;
@@ -5323,7 +5440,6 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
 	struct r5conf *conf = mddev->private;
 	sector_t logical_sector, last_sector;
 	struct stripe_head *sh;
-	int remaining;
 	int stripe_sectors;
 
 	if (mddev->reshape_position != MaxSector)
@@ -5334,7 +5450,7 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
 	last_sector = bi->bi_iter.bi_sector + (bi->bi_iter.bi_size>>9);
 
 	bi->bi_next = NULL;
-	bi->bi_phys_segments = 1; /* over-loaded to count active stripes */
+	md_write_start(mddev, bi);
 
 	stripe_sectors = conf->chunk_sectors *
 		(conf->raid_disks - conf->max_degraded);
@@ -5380,7 +5496,8 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
 				continue;
 			sh->dev[d].towrite = bi;
 			set_bit(R5_OVERWRITE, &sh->dev[d].flags);
-			raid5_inc_bi_active_stripes(bi);
+			bio_inc_remaining(bi);
+			md_write_inc(mddev, bi);
 			sh->overwrite_disks++;
 		}
 		spin_unlock_irq(&sh->stripe_lock);
@@ -5403,11 +5520,8 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
 		release_stripe_plug(mddev, sh);
 	}
 
-	remaining = raid5_dec_bi_active_stripes(bi);
-	if (remaining == 0) {
-		md_write_end(mddev);
-		bio_endio(bi);
-	}
+	md_write_end(mddev);
+	bio_endio(bi);
 }
 
 static void raid5_make_request(struct mddev *mddev, struct bio * bi)
@@ -5418,7 +5532,6 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi)
 	sector_t logical_sector, last_sector;
 	struct stripe_head *sh;
 	const int rw = bio_data_dir(bi);
-	int remaining;
 	DEFINE_WAIT(w);
 	bool do_prepare;
 	bool do_flush = false;
@@ -5440,8 +5553,6 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi)
 		do_flush = bi->bi_opf & REQ_PREFLUSH;
 	}
 
-	md_write_start(mddev, bi);
-
 	/*
 	 * If array is degraded, better not do chunk aligned read because
 	 * later we might have to read it again in order to reconstruct
@@ -5462,7 +5573,7 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi)
 	logical_sector = bi->bi_iter.bi_sector & ~((sector_t)STRIPE_SECTORS-1);
 	last_sector = bio_end_sector(bi);
 	bi->bi_next = NULL;
-	bi->bi_phys_segments = 1;	/* over-loaded to count active stripes */
+	md_write_start(mddev, bi);
 
 	prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE);
 	for (;logical_sector < last_sector; logical_sector += STRIPE_SECTORS) {
@@ -5597,16 +5708,9 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi)
 	}
 	finish_wait(&conf->wait_for_overlap, &w);
 
-	remaining = raid5_dec_bi_active_stripes(bi);
-	if (remaining == 0) {
-
-		if ( rw == WRITE )
-			md_write_end(mddev);
-
-		trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
-					 bi, 0);
-		bio_endio(bi);
-	}
+	if (rw == WRITE)
+		md_write_end(mddev);
+	bio_endio(bi);
 }
 
 static sector_t raid5_size(struct mddev *mddev, sector_t sectors, int raid_disks);
@@ -5955,7 +6059,8 @@ static inline sector_t raid5_sync_request(struct mddev *mddev, sector_t sector_n
 	return STRIPE_SECTORS;
 }
 
-static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
+static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio,
+			       unsigned int offset)
 {
 	/* We may not be able to submit a whole bio at once as there
 	 * may not be enough stripe_heads available.
@@ -5971,7 +6076,6 @@ static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
 	int dd_idx;
 	sector_t sector, logical_sector, last_sector;
 	int scnt = 0;
-	int remaining;
 	int handled = 0;
 
 	logical_sector = raid_bio->bi_iter.bi_sector &
@@ -5985,7 +6089,7 @@ static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
 		     sector += STRIPE_SECTORS,
 		     scnt++) {
 
-		if (scnt < raid5_bi_processed_stripes(raid_bio))
+		if (scnt < offset)
 			/* already done this stripe */
 			continue;
 
@@ -5993,15 +6097,15 @@ static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
 
 		if (!sh) {
 			/* failed to get a stripe - must wait */
-			raid5_set_bi_processed_stripes(raid_bio, scnt);
 			conf->retry_read_aligned = raid_bio;
+			conf->retry_read_offset = scnt;
 			return handled;
 		}
 
 		if (!add_stripe_bio(sh, raid_bio, dd_idx, 0, 0)) {
 			raid5_release_stripe(sh);
-			raid5_set_bi_processed_stripes(raid_bio, scnt);
 			conf->retry_read_aligned = raid_bio;
+			conf->retry_read_offset = scnt;
 			return handled;
 		}
 
@@ -6010,12 +6114,9 @@ static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
 		raid5_release_stripe(sh);
 		handled++;
 	}
-	remaining = raid5_dec_bi_active_stripes(raid_bio);
-	if (remaining == 0) {
-		trace_block_bio_complete(bdev_get_queue(raid_bio->bi_bdev),
-					 raid_bio, 0);
-		bio_endio(raid_bio);
-	}
+
+	bio_endio(raid_bio);
+
 	if (atomic_dec_and_test(&conf->active_aligned_reads))
 		wake_up(&conf->wait_for_quiescent);
 	return handled;
@@ -6058,7 +6159,7 @@ static int handle_active_stripes(struct r5conf *conf, int group,
 
 	for (i = 0; i < batch_size; i++)
 		handle_stripe(batch[i]);
-	r5l_write_stripe_run(conf->log);
+	log_write_stripe_run(conf);
 
 	cond_resched();
 
@@ -6075,6 +6176,7 @@ static void raid5_do_work(struct work_struct *work)
 	struct r5worker *worker = container_of(work, struct r5worker, work);
 	struct r5worker_group *group = worker->group;
 	struct r5conf *conf = group->conf;
+	struct mddev *mddev = conf->mddev;
 	int group_id = group - conf->worker_groups;
 	int handled;
 	struct blk_plug plug;
@@ -6095,6 +6197,9 @@ static void raid5_do_work(struct work_struct *work)
 		if (!batch_size && !released)
 			break;
 		handled += batch_size;
+		wait_event_lock_irq(mddev->sb_wait,
+			!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags),
+			conf->device_lock);
 	}
 	pr_debug("%d stripes handled\n", handled);
 
@@ -6122,24 +6227,13 @@ static void raid5d(struct md_thread *thread)
 
 	md_check_recovery(mddev);
 
-	if (!bio_list_empty(&conf->return_bi) &&
-	    !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) {
-		struct bio_list tmp = BIO_EMPTY_LIST;
-		spin_lock_irq(&conf->device_lock);
-		if (!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) {
-			bio_list_merge(&tmp, &conf->return_bi);
-			bio_list_init(&conf->return_bi);
-		}
-		spin_unlock_irq(&conf->device_lock);
-		return_io(&tmp);
-	}
-
 	blk_start_plug(&plug);
 	handled = 0;
 	spin_lock_irq(&conf->device_lock);
 	while (1) {
 		struct bio *bio;
 		int batch_size, released;
+		unsigned int offset;
 
 		released = release_stripe_list(conf, conf->temp_inactive_list);
 		if (released)
@@ -6157,10 +6251,10 @@ static void raid5d(struct md_thread *thread)
 		}
 		raid5_activate_delayed(conf);
 
-		while ((bio = remove_bio_from_retry(conf))) {
+		while ((bio = remove_bio_from_retry(conf, &offset))) {
 			int ok;
 			spin_unlock_irq(&conf->device_lock);
-			ok = retry_aligned_read(conf, bio);
+			ok = retry_aligned_read(conf, bio, offset);
 			spin_lock_irq(&conf->device_lock);
 			if (!ok)
 				break;
@@ -6544,6 +6638,7 @@ static int alloc_thread_groups(struct r5conf *conf, int cnt,
 
 		group = &(*worker_groups)[i];
 		INIT_LIST_HEAD(&group->handle_list);
+		INIT_LIST_HEAD(&group->loprio_list);
 		group->conf = conf;
 		group->workers = workers + i * cnt;
 
@@ -6634,8 +6729,8 @@ static void free_conf(struct r5conf *conf)
 {
 	int i;
 
-	if (conf->log)
-		r5l_exit_log(conf->log);
+	log_exit(conf);
+
 	if (conf->shrinker.nr_deferred)
 		unregister_shrinker(&conf->shrinker);
 
@@ -6646,7 +6741,10 @@ static void free_conf(struct r5conf *conf)
 		if (conf->disks[i].extra_page)
 			put_page(conf->disks[i].extra_page);
 	kfree(conf->disks);
+	if (conf->bio_split)
+		bioset_free(conf->bio_split);
 	kfree(conf->stripe_hashtbl);
+	kfree(conf->pending_data);
 	kfree(conf);
 }
 
@@ -6756,6 +6854,14 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 	conf = kzalloc(sizeof(struct r5conf), GFP_KERNEL);
 	if (conf == NULL)
 		goto abort;
+	INIT_LIST_HEAD(&conf->free_list);
+	INIT_LIST_HEAD(&conf->pending_list);
+	conf->pending_data = kzalloc(sizeof(struct r5pending_data) *
+		PENDING_IO_MAX, GFP_KERNEL);
+	if (!conf->pending_data)
+		goto abort;
+	for (i = 0; i < PENDING_IO_MAX; i++)
+		list_add(&conf->pending_data[i].sibling, &conf->free_list);
 	/* Don't enable multi-threading by default*/
 	if (!alloc_thread_groups(conf, 0, &group_cnt, &worker_cnt_per_group,
 				 &new_group)) {
@@ -6771,15 +6877,14 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 	init_waitqueue_head(&conf->wait_for_stripe);
 	init_waitqueue_head(&conf->wait_for_overlap);
 	INIT_LIST_HEAD(&conf->handle_list);
+	INIT_LIST_HEAD(&conf->loprio_list);
 	INIT_LIST_HEAD(&conf->hold_list);
 	INIT_LIST_HEAD(&conf->delayed_list);
 	INIT_LIST_HEAD(&conf->bitmap_list);
-	bio_list_init(&conf->return_bi);
 	init_llist_head(&conf->released_stripes);
 	atomic_set(&conf->active_stripes, 0);
 	atomic_set(&conf->preread_active_stripes, 0);
 	atomic_set(&conf->active_aligned_reads, 0);
-	bio_list_init(&conf->pending_bios);
 	spin_lock_init(&conf->pending_bios_lock);
 	conf->batch_bio_dispatch = true;
 	rdev_for_each(rdev, mddev) {
@@ -6813,6 +6918,9 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 			goto abort;
 	}
 
+	conf->bio_split = bioset_create(BIO_POOL_SIZE, 0);
+	if (!conf->bio_split)
+		goto abort;
 	conf->mddev = mddev;
 
 	if ((conf->stripe_hashtbl = kzalloc(PAGE_SIZE, GFP_KERNEL)) == NULL)
@@ -7097,6 +7205,13 @@ static int raid5_run(struct mddev *mddev)
 		BUG_ON(mddev->delta_disks != 0);
 	}
 
+	if (test_bit(MD_HAS_JOURNAL, &mddev->flags) &&
+	    test_bit(MD_HAS_PPL, &mddev->flags)) {
+		pr_warn("md/raid:%s: using journal device and PPL not allowed - disabling PPL\n",
+			mdname(mddev));
+		clear_bit(MD_HAS_PPL, &mddev->flags);
+	}
+
 	if (mddev->private == NULL)
 		conf = setup_conf(mddev);
 	else
@@ -7188,7 +7303,10 @@ static int raid5_run(struct mddev *mddev)
 
 	if (mddev->degraded > dirty_parity_disks &&
 	    mddev->recovery_cp != MaxSector) {
-		if (mddev->ok_start_degraded)
+		if (test_bit(MD_HAS_PPL, &mddev->flags))
+			pr_crit("md/raid:%s: starting dirty degraded array with PPL.\n",
+				mdname(mddev));
+		else if (mddev->ok_start_degraded)
 			pr_crit("md/raid:%s: starting dirty degraded array - data corruption possible.\n",
 				mdname(mddev));
 		else {
@@ -7254,14 +7372,6 @@ static int raid5_run(struct mddev *mddev)
 		mddev->queue->limits.discard_alignment = stripe;
 		mddev->queue->limits.discard_granularity = stripe;
 
-		/*
-		 * We use 16-bit counter of active stripes in bi_phys_segments
-		 * (minus one for over-loaded initialization)
-		 */
-		blk_queue_max_hw_sectors(mddev->queue, 0xfffe * STRIPE_SECTORS);
-		blk_queue_max_discard_sectors(mddev->queue,
-					      0xfffe * STRIPE_SECTORS);
-
 		blk_queue_max_write_same_sectors(mddev->queue, 0);
 		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
 
@@ -7299,14 +7409,8 @@ static int raid5_run(struct mddev *mddev)
 		blk_queue_max_hw_sectors(mddev->queue, UINT_MAX);
 	}
 
-	if (journal_dev) {
-		char b[BDEVNAME_SIZE];
-
-		pr_debug("md/raid:%s: using device %s as journal\n",
-			 mdname(mddev), bdevname(journal_dev->bdev, b));
-		if (r5l_init_log(conf, journal_dev))
-			goto abort;
-	}
+	if (log_init(conf, journal_dev, raid5_has_ppl(conf)))
+		goto abort;
 
 	return 0;
 abort:
@@ -7420,17 +7524,16 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 
 	print_raid5_conf(conf);
 	if (test_bit(Journal, &rdev->flags) && conf->log) {
-		struct r5l_log *log;
 		/*
 		 * we can't wait pending write here, as this is called in
 		 * raid5d, wait will deadlock.
+		 * neilb: there is no locking about new writes here,
+		 * so this cannot be safe.
 		 */
-		if (atomic_read(&mddev->writes_pending))
+		if (atomic_read(&conf->active_stripes)) {
 			return -EBUSY;
-		log = conf->log;
-		conf->log = NULL;
-		synchronize_rcu();
-		r5l_exit_log(log);
+		}
+		log_exit(conf);
 		return 0;
 	}
 	if (rdev == p->rdev)
@@ -7469,6 +7572,11 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 			*rdevp = rdev;
 		}
 	}
+	if (!err) {
+		err = log_modify(conf, rdev, false);
+		if (err)
+			goto abort;
+	}
 	if (p->replacement) {
 		/* We must have just cleared 'rdev' */
 		p->rdev = p->replacement;
@@ -7477,12 +7585,12 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 			   * but will never see neither - if they are careful
 			   */
 		p->replacement = NULL;
-		clear_bit(WantReplacement, &rdev->flags);
-	} else
-		/* We might have just removed the Replacement as faulty-
-		 * clear the bit just in case
-		 */
-		clear_bit(WantReplacement, &rdev->flags);
+
+		if (!err)
+			err = log_modify(conf, p->rdev, true);
+	}
+
+	clear_bit(WantReplacement, &rdev->flags);
 abort:
 
 	print_raid5_conf(conf);
@@ -7499,7 +7607,6 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	int last = conf->raid_disks - 1;
 
 	if (test_bit(Journal, &rdev->flags)) {
-		char b[BDEVNAME_SIZE];
 		if (conf->log)
 			return -EBUSY;
 
@@ -7508,9 +7615,7 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 		 * The array is in readonly mode if journal is missing, so no
 		 * write requests running. We should be safe
 		 */
-		r5l_init_log(conf, rdev);
-		pr_debug("md/raid:%s: using device %s as journal\n",
-			 mdname(mddev), bdevname(rdev->bdev, b));
+		log_init(conf, rdev, false);
 		return 0;
 	}
 	if (mddev->recovery_disabled == conf->recovery_disabled)
@@ -7537,10 +7642,12 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 		if (p->rdev == NULL) {
 			clear_bit(In_sync, &rdev->flags);
 			rdev->raid_disk = disk;
-			err = 0;
 			if (rdev->saved_raid_disk != disk)
 				conf->fullsync = 1;
 			rcu_assign_pointer(p->rdev, rdev);
+
+			err = log_modify(conf, rdev, true);
+
 			goto out;
 		}
 	}
@@ -7574,7 +7681,7 @@ static int raid5_resize(struct mddev *mddev, sector_t sectors)
 	sector_t newsize;
 	struct r5conf *conf = mddev->private;
 
-	if (conf->log)
+	if (conf->log || raid5_has_ppl(conf))
 		return -EINVAL;
 	sectors &= ~((sector_t)conf->chunk_sectors - 1);
 	newsize = raid5_size(mddev, sectors, mddev->raid_disks);
@@ -7625,7 +7732,7 @@ static int check_reshape(struct mddev *mddev)
 {
 	struct r5conf *conf = mddev->private;
 
-	if (conf->log)
+	if (conf->log || raid5_has_ppl(conf))
 		return -EINVAL;
 	if (mddev->delta_disks == 0 &&
 	    mddev->new_layout == mddev->layout &&
@@ -7658,6 +7765,9 @@ static int check_reshape(struct mddev *mddev)
 				      mddev->chunk_sectors)
 			    ) < 0)
 			return -ENOMEM;
+
+	if (conf->previous_raid_disks + mddev->delta_disks <= conf->pool_size)
+		return 0; /* never bother to shrink */
 	return resize_stripes(conf, (conf->previous_raid_disks
 				     + mddev->delta_disks));
 }
@@ -8148,6 +8258,68 @@ static void *raid6_takeover(struct mddev *mddev)
 	return setup_conf(mddev);
 }
 
+static int raid5_change_consistency_policy(struct mddev *mddev, const char *buf)
+{
+	struct r5conf *conf;
+	int err;
+
+	err = mddev_lock(mddev);
+	if (err)
+		return err;
+	conf = mddev->private;
+	if (!conf) {
+		mddev_unlock(mddev);
+		return -ENODEV;
+	}
+
+	if (strncmp(buf, "ppl", 3) == 0) {
+		/* ppl only works with RAID 5 */
+		if (!raid5_has_ppl(conf) && conf->level == 5) {
+			err = log_init(conf, NULL, true);
+			if (!err) {
+				err = resize_stripes(conf, conf->pool_size);
+				if (err)
+					log_exit(conf);
+			}
+		} else
+			err = -EINVAL;
+	} else if (strncmp(buf, "resync", 6) == 0) {
+		if (raid5_has_ppl(conf)) {
+			mddev_suspend(mddev);
+			log_exit(conf);
+			mddev_resume(mddev);
+			err = resize_stripes(conf, conf->pool_size);
+		} else if (test_bit(MD_HAS_JOURNAL, &conf->mddev->flags) &&
+			   r5l_log_disk_error(conf)) {
+			bool journal_dev_exists = false;
+			struct md_rdev *rdev;
+
+			rdev_for_each(rdev, mddev)
+				if (test_bit(Journal, &rdev->flags)) {
+					journal_dev_exists = true;
+					break;
+				}
+
+			if (!journal_dev_exists) {
+				mddev_suspend(mddev);
+				clear_bit(MD_HAS_JOURNAL, &mddev->flags);
+				mddev_resume(mddev);
+			} else  /* need remove journal device first */
+				err = -EBUSY;
+		} else
+			err = -EINVAL;
+	} else {
+		err = -EINVAL;
+	}
+
+	if (!err)
+		md_update_sb(mddev, 1);
+
+	mddev_unlock(mddev);
+
+	return err;
+}
+
 static struct md_personality raid6_personality =
 {
 	.name		= "raid6",
@@ -8170,6 +8342,7 @@ static struct md_personality raid6_personality =
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid6_takeover,
 	.congested	= raid5_congested,
+	.change_consistency_policy = raid5_change_consistency_policy,
 };
 static struct md_personality raid5_personality =
 {
@@ -8193,6 +8366,7 @@ static struct md_personality raid5_personality =
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid5_takeover,
 	.congested	= raid5_congested,
+	.change_consistency_policy = raid5_change_consistency_policy,
 };
 
 static struct md_personality raid4_personality =
@@ -8217,6 +8391,7 @@ static struct md_personality raid4_personality =
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid4_takeover,
 	.congested	= raid5_congested,
+	.change_consistency_policy = raid5_change_consistency_policy,
 };
 
 static int __init raid5_init(void)